Best Faceswapper I've Seen. ACE++ in ComfyUI.

Поделиться
HTML-код
  • Опубликовано: 5 фев 2025

Комментарии • 82

  • @ВладимирБондарь-т8ь
    @ВладимирБондарь-т8ь 11 часов назад

    Sebastian Hello! Thank you very much for this gift. This is the coolest scheme I have ever used, the facial resemblance can be achieved ideally. Good luck to you.

  • @LucisValorian
    @LucisValorian День назад +3

    Great video as always! much appreciated! The only true A.I guy that feels authentic imo

  • @Zampano2
    @Zampano2 2 дня назад +4

    Thanks for the workflow, much appreciated..!

  • @pitoko666666
    @pitoko666666 День назад

    Interesting trick (!): If you upload two identical images instead of different ones, you can subtly tweak facial details-like adding a smile or smoothing out features. The results look super natural!

  • @TyreII
    @TyreII День назад

    This was really helpful, thank you.

  • @mr.8oom
    @mr.8oom 2 дня назад

    love it, fantastic job like always. please do a video on taking a character from any game or movie, and make it realistic into any type of enviroment or scene. or you have other recomendation where to look for it. thank you

  • @legatuslabienus
    @legatuslabienus 2 дня назад +1

    You could put a little screen in the back with a community post of the day. Would also recommend some mood lighting led strips to add some colored light to your shots

  • @faustoserone635
    @faustoserone635 2 дня назад +2

    Thanks! You gain 1.000.000 points for Terry Pratchett 😀

  • @Juliant_Fusion
    @Juliant_Fusion День назад

    worked on my 3060 12GB, thanks for the workflow 🧙

  • @ThaGamingMisfit
    @ThaGamingMisfit 2 дня назад

    Wow, we're really getting close now !

  • @aghilan8018
    @aghilan8018 8 часов назад

    Hi, is it possible to make a video on how to use the local editing from ace++? Would be really helpful if you could make a video on that and all ace++ features

  • @ToG040
    @ToG040 2 дня назад

    Thank you for the awesome videos !

    • @sebastiankamph
      @sebastiankamph  2 дня назад

      Glad you like them! And for sticking around for so long you absolute gem.

  • @hatuey6326
    @hatuey6326 День назад

    Nice tuto but what about scars and tattoos ? is it possible ?

  • @dylanfrercks
    @dylanfrercks День назад

    This is really cool! The issue I am having is that when I initially run it, it goes to the image and mask preview node, but doesn't generate a final image. Any thoughts on what might be happening?

  • @MrPIXL
    @MrPIXL 2 дня назад +2

    Thank you so much Sebastian for the link of my models on your BIO

  • @DEVIANT...
    @DEVIANT... 2 дня назад +3

    forge?

    • @sebastiankamph
      @sebastiankamph  2 дня назад +1

      Not yet (or at all?). BUT you can use it in Swarm.

  • @damarcta
    @damarcta 2 дня назад

    hey, thanks for this workflow ! do i have to install something else for this to work? i downloaded all models mentioned, but the faces arent recognized. it doesnt matter which image i use as face (tried with faces and non faces), but the output image only change in small variation and looks like a basic flux face (incl. butt chin). nonetheless thanks for this quick update !

    • @damarcta
      @damarcta 2 дня назад +1

      never mind, it turned out that this doesnt work well if the faces are too small. works great with crop and stitch node (crop face from large image, inpaint new face on cropped image, stitch back to original larger image). what i dont like about pulid (and ipadapter for sd1.5/sdxl) is that it removes to much details and face do look like a pixar character most of the time

    • @sebastiankamph
      @sebastiankamph  День назад

      That's a clever solution!

  • @shahidkhanmehsood2117
    @shahidkhanmehsood2117 День назад

    How to swap clothes in videos?

  • @ihazerfeni2633
    @ihazerfeni2633 2 дня назад +1

    getting error missing node types teacacheforlmggen

    • @sebastiankamph
      @sebastiankamph  2 дня назад

      Make sure your ComfyUI is updated and you install all missing custom nodes. But Teacache is not required, you can delete it if you can't get it to install.

  • @audiovisual3937
    @audiovisual3937 2 дня назад

    Hi. Does this also work with video?

  • @nomoreterban
    @nomoreterban День назад

    nice vid. idk how this work. in my experience usually this type of stuff needs custom addons. how on earth just lora make this happen? now i remember Id spent whole day instaling pulid and results were bad. it seems this one looks a lot better than pulid's.

  • @rangorts
    @rangorts 2 дня назад

    is it possible to use this like a controlnet for img2img

  • @nicolasmarnic399
    @nicolasmarnic399 2 дня назад

    Hi, do you think this is better than FaceFusion?

  • @ai.Myikigai
    @ai.Myikigai День назад

    thx for video!like

  • @siegekeebs
    @siegekeebs 2 дня назад

    What's the minimum vram to run this? 3080 10gb is just not enough for most flux workloads =(

  • @lennoyl
    @lennoyl 2 дня назад

    Very nice workflow.
    thanks
    edit: it globally works pretty well but I had an issue when the previous face has beard and the new one doesn't: the result has beard. I'm pretty sure it can be solved by the prompt but I didn't manage to solve it.

  • @KDawg5000
    @KDawg5000 2 дня назад

    I'm OK w/Comfy, though I do hope some of these tools make their way into Forge at some point.

  • @FrtnY
    @FrtnY 2 дня назад

    Will it work on Mac M chips?🙏

  • @keysncoffee7733
    @keysncoffee7733 2 дня назад

    I thought the beard was AI 😂

  • @ashnasikri667
    @ashnasikri667 18 часов назад

    Wish I could use face swap on my grey hair too IRL

  • @orion4d727
    @orion4d727 2 дня назад

    Thank

  • @yngeneer
    @yngeneer 2 дня назад

    the best swap? so you didn't hear about PuLID II ?

    • @sebastiankamph
      @sebastiankamph  2 дня назад

      In your opinion, how do you feel about pulid 2 compared to ace++? I mean in terms of features :)

    • @ywueeee
      @ywueeee 2 дня назад +3

      @@sebastiankamph time for a comparision video of all the swappers

    • @yngeneer
      @yngeneer 2 дня назад

      @@sebastiankamph thats why I posted that comment ;-) By my point of view the PuLID II is far superior. But maybe I did something wrong previously, because, I must admitt, my results weren't by far as good as yours... I tried ace++ sometime last week...

    • @Darkwing8707
      @Darkwing8707 2 дня назад

      @@yngeneer In my opinion, PuLID is inferior. It never seems to get as close as ACE++.

    • @yngeneer
      @yngeneer 2 дня назад

      @ well, I already decided to give it second chance ;-)

  • @ChesterHunting
    @ChesterHunting 2 дня назад

    Try Inswapper 128 with roop.

    • @sebastiankamph
      @sebastiankamph  2 дня назад

      You're really bringing out my old videos eh. Brings back memories.

    • @ChesterHunting
      @ChesterHunting День назад

      @ still the best tool to swap Videos haha

  • @viper5955
    @viper5955 2 дня назад

    👍👍

  • @LouisGedo
    @LouisGedo 2 дня назад

    👋 hi 👋

  • @SebAnt
    @SebAnt 2 дня назад

    • @sebastiankamph
      @sebastiankamph  2 дня назад

      Good to see you again, you absolute superstar you!

  • @Suptuou1
    @Suptuou1 День назад

    ''ERROR lora diffusion_model.img_in.weight shape '[3072, 384]' is invalid for input of size 196608'' ERROOR!!!! What is the problem ?

  • @armondtanz
    @armondtanz 2 дня назад +1

    Please do idiots guide to comfy.
    Be good to learn this but it looks like at any moment it can go la la. 😢

  • @hotprinzify
    @hotprinzify День назад

    Not working, I made a clean ComfyUI, installed all missing Nodes and Modells, still "ERROR lora diffusion_model.img_in.weight shape '[3072, 384]' is invalid for input of size 196608"

  • @vpakarinen
    @vpakarinen 2 дня назад

    Sometimes its good to do manual work, i wouldn't automate everything specially if you want something specific and custom that AI can't do perfectly.

  • @vasilybodnar168
    @vasilybodnar168 2 дня назад +1

    Personally, I got terrible results. Either the faces don't look alike at all, or they fit into the picture terribly. ReActor does it much better and faster.

    • @TheGiovany82
      @TheGiovany82 2 дня назад

      Same bad results 😔

    • @MyComyui
      @MyComyui День назад

      i do have workflows taht works best, seems like i have to start.my channel I'm not able to share what i have. 🥺

    • @2008spoonman
      @2008spoonman День назад

      Same here, results are not good. Reactor for Flux does not exist, only for SDXL

    • @vasilybodnar168
      @vasilybodnar168 День назад +2

      @@2008spoonman Reactor doesn't care about SDXL/Flux. It just takes input image:)

    • @2008spoonman
      @2008spoonman День назад

      @@vasilybodnar168 thanks. Gonna try this with Flux 👍🏼

  • @GeekRedux
    @GeekRedux 2 дня назад

    0:47 Beard will look fine but you're going to want to shave your neck. 👍

    • @sebastiankamph
      @sebastiankamph  2 дня назад +1

      Thank you for the tip! I'll be so handsome next time you see me.

  • @avivb.m.7487
    @avivb.m.7487 2 дня назад

    What about vid to vid with Lora?

  • @mada_faka
    @mada_faka 2 дня назад

    HAHAHAHA THAT SO FUNNY SIR